Every case study, system breakdown, and field note, newest first and filterable by topic. No theory, no demos. Only systems that run in production and what it took to get them there.
This is the complete archive: all 699 posts across 62 topics, newest first, filterable by category. It holds the case studies, the model and tool comparisons, and the field notes from systems I built and run. For the curated view, where the writing sits alongside the free Claude Code skills, start at the Library instead.
The archive leans in four directions: AI Search Visibility (132), AI Agent Architecture (65), AI Tools (38), and Open Source (37). Those four account for most of what I publish, because they are where most of the client questions land.
Three places to start. The AI search visibility guide is the hub for the largest cluster and links out to every spoke in it. Grok Imagine vs Midjourney is the image model comparison, rebuilt against live leaderboard data rather than left to go stale. OutreachIQ is the longest running system breakdown here, from first prototype through to a public repo.
Alex Grankin compares shrinking frontier-model allowances with improving local models. Separate API-equivalent estimates from actual credits, then decide by cost per accepted job.
Marcin AI edits a talking-head intro with ChatCut inside ChatGPT: rough cut, motion tests, sound, and final export. Here is the workflow and what the cost claim does not show.
Andrew Warner and Alex McDonnell test three ways to bring agents into team work. Compare shared context, shared conversations, ownership, permissions, and the real cost of using ChatGPT through Hyperagent.
Greg Isenberg and Varick Agents CEO Vas Moza explain the FDE method: map real work, remove needless steps, choose code or agents deliberately, and measure the outcome.
Pat Simmons tests ChatGPT Dots on shopping, travel, project management, and inbox monitoring. Here is what completed, what stalled, and who can actually use it.
Make service packages comparable through clear scope, exclusions, evidence, timing, and approval boundaries.
Keep founder voice, taste, trade-offs, and exclusions in an AI-assisted brief so efficient drafting does not flatten the creative signal.
Igor tests a ChatGPT Dot on used-camper-van research, an hourly check, and a Space tracker. See what completed, what failed, who can access it, and a safer first workflow.
Sam Altman tells Dan Shipper how his Dot filters urgent work, builds several versions of a feature, and updates living documents. Here is what small teams can adapt without Dots or Ultrafast.
Greg Brockman and Marina Mogilko discuss building before you feel ready, turning domain expertise into an AI business, and where human judgment still matters.
Test whether a site lets a person or an agent find facts, compare services, and complete a bounded task when the interface is under pressure.
If AI Mode queries are longer and more multimodal, service pages need a clearer opening answer, stronger proof, and better internal support without collapsing into generic SEO mush.
NetworkChuck reacts live to OpenAI DevDay: Dots versus Grok Bot and Hermes, Decisions API versus Jev, GPT-6.1 Sol, Pro 500, Ultrafast, and what is still preview-only.
Futurepedia tests OpenAI Dots across Pages, Work, Codex, voice, and scheduling. See what completed, what broke, three starter use cases from the creator guide, and who can access Dots.
OpenAI DevDay 2026 announced Dots, Space, GPT-6.1 Sol, Ultrafast, Codex updates, the Agents API, plugins, and more. An official-source guide to what is available, what is limited, and three projects to try.
Matthew Berman recaps OpenAI DevDay 2026: Dots, Astra Ultrafast, Pro 500, GPT-6.1 Sol, Codex Security, plugins, Sign in with ChatGPT, and Space. Here is what is available, what costs more, and what remains a preview.
Greg Isenberg picks four OpenAI DevDay developments for builders: Dots, Decisions API, Agents API computer use, and Sign in with ChatGPT. Separate what is available from the startup thesis, then test two practical business ideas.
Andrew Warner tours nine GitHub business tools for analytics, SEO, invoicing, scheduling, billing, forms, CRM, marketing, and support. Compare the real use case, consulting offer, source links, license, and self-hosting burden.
Explore 30 linked Opus 5.5 video and motion examples, 11 Samson builds, two playable model comparisons, shared briefs, and a practical guide to choosing code, video models, or After Effects.
A practical JQ AI SYSTEMS roundup of this week's hot GitHub repos suggested by The Next New Thing: MoneyPrinterTurbo, headroom, MarkItDown, Supermemory, ECC, taste-skill, VoxCPM, and more.
AI can accelerate web production, but it can also flatten brands into the visual mean. Here is why bland AI-built sites become weaker in multimodal and AI-mediated discovery.
A structured guide to zero's Opus 5.5 motion-design workflow: references, a code-rendering studio, licensed assets, three demo formats, beat timing, and quality control.
GPT-6 Sol and Luna cut API prices, Opus 5.5 gets a five-task creator test, and Muse moves toward glasses. A sourced guide to 13 AI updates, availability, and the claims worth checking.
Andrew Warner reviews eight Muse creator demos: bill calls, price trackers, Marketplace, school PDFs, local files, family briefings, browser research, and messaging. See where delegation works and where approvals still slow it down.
Every post here is about a system that actually shipped. Book a free call and let's talk about what could ship for you.
Book Free 30-min CallAdd your name and email to unlock recording.
Your recording is emailed to me and kept on this site's server for 12 months, then deleted. Privacy policy.
Thanks for your voice message. I listen to every one myself and I will get back to you within one business day.
Explore João's services and public work, or arrange a free 30-minute consultation.
Choose a time with Cal.com. Your booking status is shown there. No calendar details are shared with this assistant.
Open booking in a new tabWhen enabled, each question is processed by Cloudflare AI and checked for abuse with Turnstile. No chat history is stored by this app. Please leave out private information.
Prepared answers · Public information